Skip to main content
1 of 8
Iosif Pinelis
  • 127.9k
  • 8
  • 107
  • 229

$\newcommand\th\theta$Indeed, the densities $f_\th:=d\mu_\th/d\nu$ are defined only $\nu$-a.e., and hence it makes no sense to define a maximum likelihood estimate (MLE) as a maximizer of $f_\th(x)$ in $\th$ for whatever versions of the densities are chosen.

Usually, though, it is assumed that versions $f_\th$ of the densities can be chosen so that the likelihood $L_x(\th):=f_\th(x)$ be regular enough in $\th$. In particular, in proofs of the consistency of the MLE, one of the standard assumptions is that the likelihood $L_x(\th)$ be continuous in $\th$; in proofs of central limit theorems for the MLE, one of the standard assumptions is that the likelihood $L_x(\th)$ be twice differentiable in $\th$.

For some textbook statistical models (that is, for some families $(\mu_\th)$), it is impossible to make $L_x(\th)$ be continuous in $\th$.

Iosif Pinelis
  • 127.9k
  • 8
  • 107
  • 229